Re: [agi] Video Mining

2007-08-03 Thread Russell Wallace
On 8/3/07, John G. Rose <[EMAIL PROTECTED]> wrote: > > Dealing with non-videoed information is very well doable, straight forward > in general; naturally there are still many issues. Image analysis > technology is there in many ways, audio speech recognition/analysis is > getting pretty good. But

Re: [agi] Active Learning

2007-08-03 Thread Benjamin Goertzel
I can't talk about details at this stage, but... We're going to start out with something pretty simple using only some particular bits of the Novamente Cognition Engine, and then roll out successive versions using more and more of the NCE ... so, at what point we will cross the borderline btw narr

Re: [agi] AI "sleep"

2007-08-03 Thread Mike Tintner
MT: I thought there were some quite well-established hypotheses (which doesn't mean that they're at all right) - by AI thinkers - that sleep might be essential for, among other things, reprocessing the events of the past day, and possibly reprogramming accordingly. > Jey I've read simila

RE: [agi] AI "sleep"

2007-08-03 Thread John G. Rose
> From: Pei Wang [mailto:[EMAIL PROTECTED] > > There was a previous discussion on this topic: > http://www.mail-archive.com/agi@v2.listbox.com/msg05028.html This light touching on the topic doesn't really do it justice. The more you think about sleep the more important it becomes depending on wh

Re: [agi] AI "sleep"

2007-08-03 Thread Jey Kottalam
On 8/3/07, Mike Tintner <[EMAIL PROTECTED]> wrote: > > >> Why would an AI need to talk to itself or 'sleep'? What function does > >> it serve? > > I thought there were some quite well-established hypotheses (which doesn't > mean that they're at all right) - by AI thinkers - that sleep might be > e

Re: [agi] AI "sleep"

2007-08-03 Thread Mike Tintner
Why would an AI need to talk to itself or 'sleep'? What function does it serve? I thought there were some quite well-established hypotheses (which doesn't mean that they're at all right) - by AI thinkers - that sleep might be essential for, among other things, reprocessing the events of the

Re: [agi] AI "sleep"

2007-08-03 Thread Pei Wang
There was a previous discussion on this topic: http://www.mail-archive.com/agi@v2.listbox.com/msg05028.html Pei On 8/3/07, John G. Rose <[EMAIL PROTECTED]> wrote: > > From: Jey Kottalam [mailto:[EMAIL PROTECTED] > > > > Why would an AI need to talk to itself or 'sleep'? What function does > > it

RE: [agi] AI "sleep"

2007-08-03 Thread John G. Rose
> From: Jey Kottalam [mailto:[EMAIL PROTECTED] > > Why would an AI need to talk to itself or 'sleep'? What function does > it serve? It's hard to understand your question without knowing the > assumptions behind your question. > I think sleep, hibernation and other types of dormancies are biolog

[agi] AI "sleep"

2007-08-03 Thread Jey Kottalam
On 8/3/07, Patrick McKown <[EMAIL PROTECTED]> wrote: > > Also do you think that an AI should have at least two distinct > 'brains' so that it can talk to itself? This talk could be it's sleep? > Why would an AI need to talk to itself or 'sleep'? What function does it serve? It's hard to understand

Re: [agi] 2006 AGI Workshop Proceedings online...

2007-08-03 Thread Patrick McKown
Just signed up for your list. Hello everybody. Question: Are there any AI software that could be recommended? I use mac osx or unix. Neural nets expert systems etc. that might be free. That are something that can be actually used. Wanted to train and AI on my area of work. I am sure this is alrea

[agi] Video Mining

2007-08-03 Thread John G. Rose
The internet is changing rapidly again. AGIs taking input off of the internet have to deal with text, audio, images, various symbologies e.g. mathematics representations, music, different types of protocalled or standardly formatted information e.g. autocad files, RFC'd communications, XML markup